julrog/nn_vis

Health v2 · maintenance only

Adoption not part of the score

1174 stars · 190 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python tool that processes trained neural networks and renders them as decluttered 3D visualizations of their architecture and parameters, using importance estimation, edge bundling, and ray tracing. It includes a desktop visualization tool with optional VR support and a Docker image.

Use cases

• visualize neural network architecture in 3d
• inspect parameters of a trained model visually
• understand which parts of a network are important
• explore deep learning models in virtual reality
• create decluttered renderings of large neural networks
• compare neural network architectures visually

When to choose

• you want an interactive 3D/VR visualization of a trained PyTorch-style model's architecture and learned importance
• you need publication-quality renderings of network structure
• you want to explore model internals beyond static diagrams

When to avoid

• you need training dashboards or scalar metrics like loss curves (use TensorBoard or W&B)
• you need a lightweight in-notebook plotting library
• you need support for arbitrary model formats without preprocessing

Facets

application · maturity maintenance

data-visualization machine-learning graphics developer-tools deep-learning data-visualization machine-learning graphics python cross-platform neural-networks opengl virtual-reality 3d-visualization model-interpretability rendering-engine docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="julrog/nn_vis")